rootpilot-ssh-diagnose
About
Read-only SSH server diagnostics: 38-command whitelist, secret-redacted.
Details
- Author
- easton-ou
- Categories
- Developer Tools, Other, Infrastructure, Cloud Service
Jump to
Setup
Install rootpilot-ssh-diagnose in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/easton-ou/rootpilot-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Read-only SSH server diagnostics: 38-command whitelist, secret-redacted.
This is the open-source, bring-your-own-LLM taste ofRootPilot. The full product adds calibrated diagnosis (89.7% across 29 standard failure scenarios, zero false alarms on healthy hosts), alert-triggered auto-diagnosis, history, and multi-host management →rootpilotx.com· deployment repo:rootpilot-release
When a server misbehaves, you end up SSH-ing in and running the same twenty commands —df -h,docker ps,dmesg | grep -i oom,free -m— then eyeballing the output. This server turns that into a conversation: your LLM asks for exactly the evidence it needs, gets structured, secret-redacted output back, and reasons about the root cause. You stay in control; nothing leaves your machine except SSH to your own hosts.
- Read-only whitelist.There are exactly 38 built-in commands (get_whitelistlists them all). There is no tool that runs an arbitrary command — not even with a confirmation prompt. Every command only inspects state.
- The only injectable value is a container name, validated against^[a-zA-Z0-9_.-]+$before it is ever placed in a command.web; rm -rf /is rejected, not escaped.
- Secrets are redactedfrom output before it reaches your model:KEY=valuesecrets,Bearer/Basictokens,sk-/ghp_/AKIA…key shapes, PEM private-key blocks, and credentials embedded in URLs.docker inspectenv values are scrubbed.
- Per-command timeout(15s) and output truncation guard against hangs and floods.
- Credentials stay local.Host definitions live in a file you control; passwords are never logged.
Add the server to your MCP client. ForClaude Desktop(claude_desktop_config.json):
{ "mcpServers": { "rootpilot-ssh-diagnose": { "command": "npx", "args": ["-y", "@rootpilot/mcp-ssh-diagnose"], "env": { "RP_HOSTS": "/Users/me/.rootpilot-mcp/hosts.json" } } } }
Then createhosts.json(seehosts.example.json):
[ { "name": "prod-1", "host": "1.2.3.4", "port": 22, "user": "rootpilot", "auth": { "type": "key", "keyPath": "~/.ssh/rootpilot_key" } }, { "name": "prod-2", "host": "10.0.0.5", "user": "ops", "auth": { "type": "password", "password": "..." } } ]
Restart your client. Ask it:"Diagnose prod-1"(or run thediagnose-hostprompt).
Use a least-privilege account.Create a dedicated read-only SSH user for diagnostics rather than reusing root. The commands only read state, but the account should reflect that.
Two prompts ship built-in:diagnose-host(evidence-first root-cause walkthrough) andhealth-check(a light sweep).
your MCP client (the LLM) │ "collect df, docker_ps, dmesg_oom from prod-1" ▼ rootpilot-ssh-diagnose ──ssh──▶ your server │ renders a whitelisted template, runs it read-only, │ redacts secrets, truncates, returns structured output ▼ the LLM reasons about root cause from the evidence
The server deliberately doesnoanalysis of its own — no built-in LLM call, no multi-round orchestration. That boundary is the point: it's a clean, auditable evidence collector. Calibrated diagnosis (decidingwhichevidence to pull forwhichsymptom, across follow-up rounds, scored against a failure-scenario library) is what the fullRootPilotproduct does.
Does it ever change my server?No. Every command is read-only, and there is no arbitrary-command tool. The full whitelist is visible viaget_whitelist.
Where does my data go?Nowhere except SSH between this server (running on your machine) and your hosts. Command output goes to your MCP client's model. No telemetry.
Which LLM does it use?None of its own — it's bring-your-own. Whatever model your MCP client runs does the reasoning.
Can it manage Windows servers or jump hosts?Not in v1. It targets Linux hosts over direct SSH.
How is this different from RootPilot?This collects evidence; you (or your model) interpret it ad hoc. RootPilot adds calibrated diagnosis, alert-triggered auto-diagnosis, a per-host history ("medical record"), and multi-host management. Seerootpilotx.com.
npm install npm run build # compile to dist/ npm test # whitelist / injection / redaction / timeout tests npm run typecheck
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
AI-native network automation for MikroTik RouterOS. MikroMCP exposes RouterOS as a typed, auditable Model Context Protocol server so Claude, Cursor, Codex, and other MCP clients can inspect, diagnose, and safely operate MikroTik routers in natural language.
An MCP server that provides SSH-based remote management tools, acting as proxy
Model Context Protocol server for secure AsusWRT router administration via SSH. Provides 42+ read-only monitoring tools and guarded mutation tools for managing AsusWRT/Merlin routers.
DevOps MCP — Secure MCP Server for Linux Server Automation
A three-tier access control MCP server that allows AI assistants (Claude Code, Cursor, Windsurf) to safely scan, plan, and operate Linux servers via SSH without full write access. Includes an out-of-band human consent token gate, automated port-conflict scanning, and a completely read-only default safe mode to eliminate accidental destructive commands on production environments.
Integrate with Foreman to manage hosts and other infrastructure resources.
Manage and monitor homelab systems via SSH.
The official Impreza Host connector for offshore server management
A local MCP server that securely connects to remote servers over SSH, acting as a proxy for MCP commands.
MCP (Model Context Protocol) server for managing VPS servers via the mikr.us API and remote Linux servers over SSH. Built in Python, runs anywhere — locally, in Docker, or as a Claude Desktop integration.
A remote Model Context Protocol (MCP) server for managing VPS servers and domains on Sitequest. Lets AI assistants provision, monitor, and configure infrastructure through natural language.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
